Method and device for identifying performance of laser radar, vehicle and storage medium

Abstract

The application discloses a performance identification method and device of a laser radar, a vehicle and a storage medium. The method comprises the following steps: determining a non-identification blind area of the laser radar; when no target object is placed in the non-identification blind area, calculating a point cloud distribution of the non-identification blind area according to characteristic information of the laser radar and characteristic information of the ground to obtain an ideal unobstructed point cloud distribution; when a target object is placed in the non-identification blind area, removing obstructed point clouds of the target object from the ideal unobstructed point cloud distribution to obtain an ideal obstructed point cloud distribution, and obtaining a point cloud distribution of the non-identification blind area measured by the laser radar to obtain an actual obstructed point cloud distribution; identifying a water accumulation area and a damp area from the non-identification blind area according to the ideal obstructed point cloud distribution and the actual obstructed point cloud distribution; and determining a performance identification result of the laser radar according to an area of the water accumulation area and an area of the damp area. That is, the scheme of the application can identify the performance of the laser radar, thereby enhancing the practicability and reliability of the laser radar.

Description

Technical Field

[0001] The present application relates to autonomous driving technology, and in particular to a laser radar performance identification method, device, vehicle, and storage medium. Background Art

[0002] LiDAR is one of the commonly used sensors in autonomous driving. It has the advantages of high measurement accuracy and long detection distance. Currently, most on-board LiDARs operate in the near-infrared band. On rainy days, due to factors such as raindrops and wet ground, water accumulates on the ground or it is slippery, which reduces the detection performance of LiDAR, resulting in a decline in detection results and affecting the safety of autonomous driving functions.

[0003] In existing technologies, lidar can be used to detect the depth of accumulated water or calculate the unevenness of the ground to improve safety. However, this does not take into account that the performance of lidar will be reduced due to factors such as raindrops and wet ground, resulting in a decrease in detection effectiveness on rainy days. Summary of the Invention

[0004] The present application provides a laser radar performance identification method, device, vehicle and storage medium, which can determine the non-identification blind spots of the laser radar, determine the water accumulation area and the wet area by calculating the point cloud distribution of the non-identification blind spots in various situations, and then identify the laser radar performance according to the area of ​​each area, thereby enhancing the practicality and reliability of the laser radar.

[0005] In a first aspect, the present application provides a method for identifying performance of a laser radar, the method comprising:

[0006] Determining a non-identification blind area of ​​the laser radar;

[0007] When no target object is placed in the non-identification blind area, the point cloud distribution of the non-identification blind area is calculated according to the characteristic information of the laser radar and the characteristic information of the ground to obtain an ideal unobstructed point cloud distribution;

[0008] When the target object is placed in the non-identification blind area, the occluded point cloud of the target object is removed from the ideal unobstructed point cloud distribution to obtain an ideal occluded point cloud distribution, and the point cloud distribution of the non-identification blind area measured by the laser radar is obtained to obtain an actual occluded point cloud distribution;

[0009] Identifying a waterlogged area and a wet area from the non-identification blind area according to the ideal obstructed point cloud distribution and the actual obstructed point cloud distribution;

[0010] The performance identification result of the laser radar is determined according to the area of ​​the water accumulation area and the area of ​​the wet area.

[0011] In a second aspect, the present application provides a performance identification device for a laser radar, comprising:

[0012] A determination module, configured to determine a non-identification blind area of ​​the laser radar;

[0013] An unobstructed distribution module is used to calculate the point cloud distribution of the non-identification blind area according to the characteristic information of the laser radar and the characteristic information of the ground when no target object is placed in the non-identification blind area, so as to obtain an ideal unobstructed point cloud distribution;

[0014] an occlusion distribution module, configured to, when the target object is placed in the non-identification blind zone, remove the occlusion point cloud of the target object from the ideal unobstructed point cloud distribution to obtain an ideal occlusion point cloud distribution, and obtain the point cloud distribution of the non-identification blind zone measured by the laser radar to obtain an actual occlusion point cloud distribution;

[0015] an area recognition module, configured to recognize a waterlogged area and a wet area from the non-identification blind area according to the ideal obstructed point cloud distribution and the actual obstructed point cloud distribution;

[0016] A result recognition module is used to determine the performance recognition result of the laser radar according to the area of ​​the water accumulation area and the area of ​​the wet area.

[0017] In a third aspect, the present application also provides a vehicle comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, a performance identification method for a laser radar as described in any one of the present applications is implemented.

[0018] In a fourth aspect, the present application also provides a computer-readable storage medium on which a computer program is stored, which, when executed by a processor, implements a performance identification method for a laser radar as described in any one of the present applications.

[0019] The solution of the present application determines the non-identification blind area of ​​the laser radar; when no target object is placed in the non-identification blind area, the point cloud distribution of the non-identification blind area is calculated based on the characteristic information of the laser radar and the characteristic information of the ground to obtain an ideal unobstructed point cloud distribution; when a target object is placed in the non-identification blind area, the occluded point cloud of the target object is removed from the ideal unobstructed point cloud distribution to obtain an ideal obstructed point cloud distribution, and the point cloud distribution of the non-identification blind area measured by the laser radar is obtained to obtain an actual obstructed point cloud distribution; based on the ideal obstructed point cloud distribution and the actual obstructed point cloud distribution, water accumulation areas and wet areas are identified from the non-identification blind area; and the performance identification result of the laser radar is determined based on the area of ​​the water accumulation area and the area of ​​the wet area. That is, the solution of the present application can determine the non-identification blind area of ​​the laser radar, determine the water accumulation area and the wet area by calculating the point cloud distribution of the non-identification blind area in various situations, and then identify the laser radar performance based on the area of ​​each area, thereby enhancing the practicality and reliability of the laser radar. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solution of the present application, the following is a brief introduction to the drawings required for use in the embodiments. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without paying any creative work.

[0021] Figure 1 This is a flow chart of the performance identification method of the laser radar provided in this application;

[0022] Figure 2a It is a flow chart of the method for determining the waterlogged area provided in this application;

[0023] Figure 2b This is an example diagram of the ideal occluded point cloud distribution provided by this application;

[0024] Figure 2c This is an example diagram of the actual occluded point cloud distribution provided by this application;

[0025] Figure 2d This is an example diagram of the second point cloud missing area in the actual occluded point cloud distribution provided by this application;

[0026] Figure 2e This is an example diagram of the laser beam reflection of the laser radar provided in this application;

[0027] Figure 3 It is a flow chart of a method for determining a wet area provided by the present application;

[0028] Figure 4This is another flowchart of the laser radar performance identification method provided by this application;

[0029] Figure 5 This is a schematic diagram of the structure of the performance identification device of the laser radar provided in this application;

[0030] Figure 6 It is another structural schematic diagram of the vehicle provided in this application. DETAILED DESCRIPTION

[0031] The present application will be further described in detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are intended only to illustrate the present application and are not intended to limit the present application. It should also be noted that, for ease of description, the accompanying drawings only illustrate portions of the present application, not all of the structures.

[0032] Figure 1 This is a flow chart of the performance identification method of the laser radar provided in this application. This method can be executed by the performance identification device of the laser radar provided in this application. The device can be implemented in software and / or hardware. In a specific embodiment, the device can be integrated into a vehicle and specifically applied in rainy scenes. The following embodiments will be described using the device integrated into a vehicle as an example. Figure 1 , the method may specifically include the following steps:

[0033] Step 101: determine the non-identification blind area of ​​the laser radar.

[0034] Among them, the non-identification blind area refers to the area that can be identified by the lidar.

[0035] Specifically, the laser radar is tested in an open, flat and dry test site to determine the laser radar's recognition blind area. The area that the laser radar can recognize is the laser radar's non-recognition blind area.

[0036] For example, when testing a vehicle-mounted laser radar, the laser radar blind area formed by the vehicle's own occlusion is the recognition blind area of ​​the vehicle-mounted laser radar, and the remaining area that can be recognized by the laser radar is the laser radar's non-recognition blind area.

[0037] Step 102 : When there is no target object in the non-identification blind area, the point cloud distribution of the non-identification blind area is calculated based on the characteristic information of the laser radar and the characteristic information of the ground to obtain an ideal unobstructed point cloud distribution.

[0038] The LiDAR feature information includes the LiDAR calibration information, the original point cloud information of the current frame, and the ground point cloud obtained after processing by the perception algorithm. The ground feature information includes the ground equation.

[0039] Specifically, when there is no target object in the non-identification blind spot, the point cloud distribution of the non-identification blind spot is calculated based on the calibration information of the lidar, the original point cloud information of the current frame, and the ground point cloud obtained after processing by the perception algorithm, combined with the ground equation, which is the ideal unobstructed point cloud distribution.

[0040] For example, when obtaining the ideal unobstructed point cloud distribution of a vehicle-mounted lidar, it is necessary to obtain the point cloud distribution of the non-identification blind spot of the vehicle-mounted lidar based on the calibration information of the lidar, the original point cloud information of the current frame, and the ground point cloud, ground equations and vehicle motion data obtained after processing by the perception algorithm, such as vehicle speed, yaw angle, etc., which is the ideal unobstructed point cloud distribution.

[0041] Step 103: When a target object is placed in a non-identification blind spot, the occluded point cloud of the target object is removed from the ideal unobstructed point cloud distribution to obtain an ideal occluded point cloud distribution, and the point cloud distribution of the non-identification blind spot measured by the lidar is obtained to obtain an actual occluded point cloud distribution.

[0042] Optionally, when the target object is placed in the non-identification blind area, bounding box information of the target object is obtained; and the occlusion point cloud of the target object is calculated based on the bounding box information of the target object.

[0043] Specifically, after placing the target object in the non-identification blind spot, the bounding box information of the target object is obtained through the laser radar, and then the occlusion point cloud of the target object is calculated based on the bounding box information of the target object.

[0044] For example, any object is placed in the non-identification blind spot of the laser radar. The object is the target object. The bounding box information of the target object is obtained through the laser radar, and then the occlusion point cloud of the target object is calculated based on the bounding box information of the target object.

[0045] After obtaining the occluded point cloud of the target object, the occluded point cloud of the target object is removed from the ideal unobstructed point cloud distribution, and the remaining point cloud distribution is the ideal occluded point cloud distribution; the point cloud distribution of the non-identification blind area obtained by the lidar in the actual measurement is obtained to obtain the actual occluded point cloud distribution.

[0046] For example, after placing a target object in a non-identification blind spot, the occluded point cloud of the target object is removed from the ideal unobstructed point cloud distribution, and the lidar obtains an ideal occluded point cloud distribution; while in actual measurement, the point cloud distribution of the non-identification blind spot obtained by the lidar is the actual occluded point cloud distribution.

[0047] Step 104 : identifying the waterlogged area and the wet area from the non-identification blind area according to the ideal obstructed point cloud distribution and the actual obstructed point cloud distribution.

[0048] Optionally, a first point cloud missing area is determined from the actual obstructed point cloud distribution according to the ideal obstructed point cloud distribution; the ratio of the number of points in the first point cloud missing area to the number of points in the ideal obstructed point cloud distribution is calculated; if the ratio exceeds a preset value, a second point cloud missing area is determined from the unobstructed area of ​​the actual obstructed point cloud distribution according to the ideal obstructed point cloud distribution; when the area of ​​the second point cloud missing area exceeds the preset area value, the second point cloud missing area is determined as a potential water accumulation area.

[0049] Specifically, after obtaining the ideal occluded point cloud distribution and the actual occluded point cloud distribution, by comparing the ideal occluded point cloud distribution and the actual occluded point cloud distribution, the area where the point cloud is missing in the actual occluded point cloud distribution and the ideal occluded point cloud distribution is obtained, which is the first point cloud missing area; the number of points in the first point cloud missing area is obtained, and then the number of points in the ideal occluded point cloud distribution is obtained, and the ratio of the two is calculated; when the ratio exceeds a preset value, by comparing the ideal occluded point cloud distribution and the actual occluded point cloud distribution, the area where the point cloud distribution exists in the ideal occluded point cloud distribution but does not exist in the actual occluded point cloud distribution is obtained, which is the second point cloud missing area; after determining the second point cloud missing area, the area of ​​the second point cloud missing area is determined, and when the area exceeds the preset area value, the second point cloud missing area is determined as a potential water accumulation area.

[0050] Optionally, the number of laser beams reflected in the potential water accumulation area is obtained; a preset point cloud is obtained based on the characteristic information of the ground and the actual distribution of obstructed point clouds; the preset point clouds are clustered to obtain a preset point cloud cluster; when the number of point clouds in the preset point cloud cluster exceeds a point cloud number threshold, the point clouds in the preset point cloud cluster are projected to a preset height above the ground based on the characteristic information of the ground to obtain a projected point cloud distribution; when the positional characteristics of the projected point cloud distribution match the actual positional characteristics of the obstructed point cloud distribution, the number of laser beams reflected by the lidar in the potential water accumulation area is calculated; when the number of laser beams exceeds the laser number threshold, the potential water accumulation area is determined as a water accumulation area.

[0051] Specifically, after determining the potential water accumulation area, according to the actual occluded point cloud distribution and the ground feature information such as the ground height information, the point cloud with a height lower than the ground in the actual occluded point cloud is obtained as a preset point cloud; the preset point cloud is clustered to obtain a plurality of preset point cloud clusters; the number of point clouds in the preset point cloud cluster is obtained, and when the number of point clouds in the preset point cloud cluster exceeds a point cloud number threshold, the point clouds in the preset point cloud cluster are projected to a preset height above the ground according to the feature information of the ground, to obtain a projected point cloud distribution, wherein the preset height is calculated according to the projected point cloud information and the ground feature information; the projected point cloud distribution is compared with the actual occluded point cloud distribution, and when the position features of the two are matched, it is indicated that the laser beams detected by the laser radar are reflected and refracted in the presence of water, so that the point cloud with a height below the ground can be projected above the ground, the height from the ground is the same as the height of the projected point cloud below the ground, to obtain the projected point cloud distribution matched with the position features of the actual occluded point cloud distribution. At this time, the number of laser beams reflected by the laser radar in the potential water accumulation area is calculated according to the preset point cloud; if the number of laser beams exceeds a laser number threshold, the potential water accumulation area is determined as a water accumulation area.

[0052] Optionally, the water accumulation area is removed from the potential water accumulation area to obtain a remaining potential water accumulation area; point clouds in a preset range around the remaining potential water accumulation area are obtained to obtain preset range point clouds; a reflection intensity mean value of the preset range point clouds is calculated; if the reflection intensity mean value is lower than an intensity mean value threshold, the remaining potential water accumulation area is recorded as an observation area; the number of times that the remaining potential water accumulation area is recorded as the observation area is counted; when the number of times exceeds a number of times threshold, the remaining potential water accumulation area is determined as a wet area.

[0053] Specifically, after determining the water accumulation area, the water accumulation area is removed from the potential water accumulation area to obtain a remaining potential water accumulation area; a point cloud distribution in a preset range around the remaining potential water accumulation area is obtained as a preset range point cloud; a reflection intensity of the preset range point cloud of the laser radar is obtained, and a mean value of the reflection intensity of the preset range point cloud is calculated; when there is a water surface in the preset range, the reflection intensity of the point cloud emitted by the laser radar will be lower than the reflection intensity of the ground, so that the reflection intensity mean value of the preset range point cloud will also be lower than the reflection intensity of the ground; if the reflection intensity mean value is lower than an intensity mean value threshold, the remaining potential water accumulation area is recorded as an observation area; after the observation area is marked for multiple times, the number of times that the remaining potential water accumulation area is recorded as the observation area is counted, and if the number of times exceeds a number of times threshold, the remaining potential water accumulation area is determined as a wet area.

[0054] Step 105, determining the performance recognition result of the laser radar according to the area of the water accumulation area and the area of the wet area.

[0055] Optionally, obtain the area of ​​the waterlogged area and the area of ​​the wet area; obtain the area of ​​the ideal obstructed point cloud distribution area; calculate the ratio of the area of ​​the waterlogged area to the area of ​​the ideal obstructed point cloud distribution area to obtain a first area ratio; calculate the ratio of the area of ​​the wet area to the area of ​​the ideal obstructed point cloud distribution area to obtain a second area ratio; when the first area ratio and / or the second area ratio exceeds a preset ratio threshold, determine that the performance of the lidar does not meet the standards.

[0056] Specifically, after determining the waterlogged area and the wet area, the area of ​​the waterlogged area and the area of ​​the wet area are obtained, and then the area of ​​the ideal obstructed point cloud distribution area of ​​the current lidar is obtained, and the ratio of the area of ​​the waterlogged area to the area of ​​the ideal obstructed point cloud distribution area is calculated, and then the ratio of the area of ​​the wet area to the area of ​​the ideal obstructed point cloud distribution area is calculated. When any ratio of the two exceeds the preset ratio threshold, it is determined that the performance of the lidar does not meet the standards.

[0057] The solution of the present application determines the non-identification blind area of ​​the laser radar; when no target object is placed in the non-identification blind area, the point cloud distribution of the non-identification blind area is calculated based on the characteristic information of the laser radar and the characteristic information of the ground to obtain an ideal unobstructed point cloud distribution; when a target object is placed in the non-identification blind area, the occluded point cloud of the target object is removed from the ideal unobstructed point cloud distribution to obtain an ideal obstructed point cloud distribution, and the point cloud distribution of the non-identification blind area measured by the laser radar is obtained to obtain an actual obstructed point cloud distribution; based on the ideal obstructed point cloud distribution and the actual obstructed point cloud distribution, water accumulation areas and wet areas are identified from the non-identification blind area; and the performance identification result of the laser radar is determined based on the area of ​​the water accumulation area and the area of ​​the wet area. That is, the solution of the present application can determine the non-identification blind area of ​​the laser radar, determine the water accumulation area and the wet area by calculating the point cloud distribution of the non-identification blind area in various situations, and then identify the laser radar performance based on the area of ​​each area, thereby enhancing the practicality and reliability of the laser radar.

[0058] The following is a detailed description of a method for determining the waterlogged area. Figure 2a As shown, Figure 1 Step 104 in the embodiment may include the following steps:

[0059] Step 201 : determining a first point cloud missing region from the actual occluded point cloud distribution according to the ideal occluded point cloud distribution.

[0060] Specifically, after obtaining the ideal occluded point cloud distribution and the actual occluded point cloud distribution, by comparing the ideal occluded point cloud distribution and the actual occluded point cloud distribution, it is obtained that the area where the point cloud distribution exists in the ideal occluded point cloud distribution but does not exist in the actual occluded point cloud distribution is the first point cloud missing area.

[0061] For example, Figure 2b For the ideal occluded point cloud distribution, Figure 2c For the actual distribution of occluded point clouds, compare Figure 2b and Figure 2c It can be obtained that the area A where points P6, P8, P9, and P14 are located is the first point cloud missing area.

[0062] Step 202 : Calculate the ratio of the number of points in the missing area of ​​the first point cloud to the number of points in the ideal occluded point cloud distribution.

[0063] Specifically, the number of points in the missing area of ​​the first point cloud is obtained, and then the number of points in the ideal occluded point cloud distribution is obtained, and the ratio of the two is calculated.

[0064] For example, Figure 2b and Figure 2c As shown, the number of points in the missing area of ​​the first point cloud is 4, and the number of points in the ideal occluded point cloud distribution is 16, so the ratio between the two is 4 / 16.

[0065] Step 203 : If the ratio exceeds a preset value, a second point cloud missing area is determined from the unobstructed area where the obstructed point cloud is actually distributed according to the number of points in the first point cloud missing area.

[0066] The preset value is a preset ratio threshold for determining the missing area of ​​the second point cloud. For example, the preset value may be 0.05.

[0067] Specifically, when the ratio exceeds a preset value, an area where the number of point clouds meets the preset number of point clouds is screened out from the first point cloud missing area in the actual distribution of the occluded point cloud to obtain a second point cloud missing area.

[0068] The preset number of point clouds is a point cloud number threshold for determining the missing area of ​​the second point cloud.

[0069] For example, Figure 2c The middle area A is the missing area of ​​the first point cloud. Figure 2d The area B where the midpoints P8, P9, and P14 are located is the second point cloud missing area.

[0070] Step 204 : When the area of ​​the second point cloud missing region exceeds a preset area value, the second point cloud missing region is determined as a potential water accumulation area.

[0071] Among them, the preset area value is the area threshold for determining the potential waterlogging area.

[0072] Specifically, after determining the second point cloud missing region, the area of ​​the second point cloud missing region is determined, and when the area exceeds a preset area value, the second point cloud missing region is determined as a potential water accumulation area.

[0073] For example, the second point cloud missing area is 2m 2 , and the preset area value is 1m 2 , the second point cloud missing area is determined as a potential water accumulation area.

[0074] Step 205, obtaining the point cloud distribution of the potential water accumulation area.

[0075] Specifically, after determining the potential water accumulation area, the point cloud distribution of the potential water accumulation area is obtained according to the data measured by the laser radar.

[0076] Step 206, obtaining the preset point cloud in the potential water accumulation area according to the feature information of the ground and the point cloud distribution of the potential water accumulation area.

[0077] Specifically, the feature information of the ground includes ground height information and ground equation, and the preset point cloud in the potential water accumulation area is obtained according to the point cloud distribution of the potential water accumulation area and the feature information of the ground such as the ground height information.

[0078] For example, according to the ground height information and the point cloud distribution of the potential water accumulation area, the point cloud at a position lower than the ground height is taken as the preset point cloud in the potential water accumulation area.

[0079] Step 207, clustering the preset point cloud to obtain a preset point cloud cluster.

[0080] Specifically, the preset point cloud is clustered to obtain a plurality of preset point cloud clusters according to the feature information of the point cloud obtained by the laser radar.

[0081] For example, there are three preset point clouds, and the mutual distance between them is less than the clustering threshold, so the three preset point clouds are clustered to obtain a preset point cloud cluster.

[0082] Step 208, when the number of point clouds in the preset point cloud cluster exceeds the point cloud number threshold, projecting the point clouds in the preset point cloud cluster to a position higher than the preset height of the ground according to the feature information of the ground to obtain a projected point cloud distribution.

[0083] For example, the point cloud number threshold can be 10.

[0084] Specifically, after obtaining a plurality of preset point cloud clusters, the number of point clouds in the preset point cloud cluster is obtained, and when the number of point clouds in the preset point cloud cluster exceeds the point cloud number threshold, the point clouds in the preset point cloud cluster are projected in combination with the feature information of the ground, such as projecting the point clouds to a position higher than the preset height of the ground in combination with the ground equation, the preset height being a height calculated according to the preset point cloud and the ground equation, to obtain a projected point cloud distribution.

[0085] For example, the threshold value of the number of point clouds is 10, and the number of point clouds in the preset point cloud cluster is 20. Then the 20 preset point clouds in the preset point cloud cluster are projected onto the ground, and the height from the ground is the same as the height of the preset point cloud below the ground. The obtained point cloud distribution is the projected point cloud distribution.

[0086] Step 209 : When the projected point cloud distribution matches the position features of the actual obstructed point cloud distribution, the number of laser beams reflected by the laser radar in the potential water accumulation area is calculated.

[0087] Specifically, after obtaining the projected point cloud distribution, the projected point cloud distribution is compared with the actual obstructed point cloud distribution. If the positional features of the two match, it indicates that the point cloud detected by the lidar was reflected and refracted in the presence of water. Therefore, the point cloud can be projected onto the ground to obtain a projected point cloud distribution that matches the positional features of the actual obstructed point cloud distribution. At this time, the preset point cloud corresponding to the projected point cloud is obtained. Based on the straight line equation of the laser beam to which the preset point cloud belongs, the position of the intersection of the laser beam and the ground is calculated, the potential water accumulation area through which the laser beam passes is determined, and the number of laser beams reflected by the lidar in the potential water accumulation area is obtained.

[0088] Step 210 : When the number of laser beams exceeds a laser number threshold, the potential water accumulation area is determined as a water accumulation area.

[0089] For example, the threshold value of the number of laser beams is 5 beams.

[0090] Specifically, after calculating the number of laser beams reflected by the laser radar in the potential water accumulation area, if the number of laser beams exceeds a laser number threshold, the potential water accumulation area is determined to be a water accumulation area.

[0091] For example, the relationship between the actual object detected by the lidar and the mirrored object detected due to water reflection is as follows: Figure 2e As shown, when there is water in the potential water accumulation area, the laser beam emitted by the lidar will be reflected, thereby obtaining a mirror object detected due to the reflection of the water, which interferes with the work of the lidar. Therefore, when the number of laser beams emitted by the lidar exceeds the threshold, it indicates that there is water in the potential water accumulation area.

[0092] Alternatively, one method of determining wet areas can be as follows Figure 3 As shown, the following steps may be included:

[0093] Step 301: remove the water accumulation area from the potential water accumulation area to obtain the remaining potential water accumulation area.

[0094] Specifically, after the waterlogging area is determined, the waterlogging area is removed from the potential waterlogging area to obtain the remaining potential waterlogging area.

[0095] Step 302: Acquire a point cloud within a preset range around the remaining potential waterlogging area to obtain a point cloud within the preset range.

[0096] The preset range refers to a certain range around the potential waterlogging area. For example, the preset range can be 1m around the potential waterlogging area. 2 within the range.

[0097] Specifically, after the remaining potential waterlogging area is obtained, the point cloud distribution within a preset range around the remaining potential waterlogging area is obtained as the preset range point cloud.

[0098] Step 303: Calculate the mean reflection intensity of the point cloud within a preset range.

[0099] Specifically, after obtaining the preset range point cloud, the LiDAR point cloud reflection intensity within the preset range is obtained, and then the reflection intensity of the preset range point cloud is averaged. If there is water within the preset range, the reflection intensity of the LiDAR point cloud will be lower than the reflection intensity of the ground, so the calculated average reflection intensity of the preset range point cloud will also be lower than the reflection intensity of the ground.

[0100] In step 304, if the reflection intensity mean is lower than the intensity mean threshold, the remaining potential waterlogging area is recorded as an observation area.

[0101] Specifically, after obtaining the reflection intensity mean of the point cloud within a preset range, if the reflection intensity mean is lower than the intensity mean threshold, the remaining potential waterlogging area is recorded as the observation area.

[0102] Step 305: Count the number of times the remaining potential waterlogging areas are recorded as observation areas.

[0103] Specifically, the processing from step 302 to step 304 is performed multiple times on the remaining potential waterlogging areas, and the number of times the remaining potential waterlogging areas are recorded as observation areas is counted.

[0104] For example, during the use of the vehicle-mounted lidar, the position changes of the remaining potential water accumulation areas are calculated based on the movement of the vehicle, and the number of times the area is recorded as an observation area is counted.

[0105] Step 306: When the number of times exceeds the threshold, the remaining potential water accumulation area is determined as a wet area.

[0106] For example, the number threshold may be 5 times.

[0107] Specifically, after counting the number of times the remaining potential water accumulation area is recorded as an observation area, if the number exceeds a number threshold, the remaining potential water accumulation area is determined as a wet area; if the number does not exceed the number threshold, no processing is performed.

[0108] In this embodiment, potential waterlogging areas are calculated based on the ideal and actual obstructed point cloud distributions. A projected point cloud distribution is then calculated based on the point cloud distribution of the potential waterlogging areas, and the waterlogging areas are determined based on the projected point cloud distribution. A preset range of point clouds is then acquired within the remaining potential waterlogging areas, and the wet areas are determined based on the reflection intensity of the point clouds within the preset range. By calculating the point cloud distribution of non-blind areas in various scenarios, the waterlogging and wet areas are determined, providing a foundation for subsequently determining the performance of the LiDAR based on the area of ​​the waterlogging and wet areas.

[0109] Figure 4 This is another flow chart of the performance identification method of the laser radar provided in this application. Figure 1 The steps are refined and a method for determining the performance of the lidar based on the area of ​​the waterlogged area and the area of ​​the wet area is introduced in detail, such as Figure 4 As shown, the method may include the following steps:

[0110] Step 401: determine the non-identification blind area of ​​the laser radar.

[0111] Specifically, the laser radar is tested in an open, flat and dry test site to determine the laser radar's recognition blind area. The area that the laser radar can recognize is the laser radar's non-recognition blind area.

[0112] Step 402 : When there is no target object in the non-identification blind area, the point cloud distribution of the non-identification blind area is calculated based on the characteristic information of the laser radar and the characteristic information of the ground to obtain an ideal unobstructed point cloud distribution.

[0113] Specifically, when there is no target object in the non-identification blind spot, the point cloud distribution of the non-identification blind spot is calculated based on the calibration information of the lidar, the original point cloud information of the current frame, and the ground point cloud obtained after processing by the perception algorithm, combined with the ground equation, which is the ideal unobstructed point cloud distribution.

[0114] Step 403: Obtain bounding box information of the target object.

[0115] Specifically, after placing the target object in the non-identification blind spot, the bounding box information of the target object is obtained through the laser radar.

[0116] For example, any object is placed in the non-identification blind area of ​​the laser radar. The object is the target object, and the bounding box information of the target object is obtained through the laser radar.

[0117] Step 404 : Calculate the occlusion point cloud of the target object based on the bounding box information of the target object.

[0118] Specifically, after obtaining the bounding box information of the target object, the occlusion point cloud of the target object is calculated according to the bounding box information of the target object.

[0119] Step 405: When the target object is placed in the non-identification blind spot, the occluded point cloud of the target object is removed from the ideal unobstructed point cloud distribution to obtain the ideal occluded point cloud distribution, and the point cloud distribution of the non-identification blind spot measured by the lidar is obtained to obtain the actual occluded point cloud distribution.

[0120] Specifically, after obtaining the occluded point cloud of the target object, the occluded point cloud of the target object is removed from the ideal unobstructed point cloud distribution, and the remaining point cloud distribution is the ideal occluded point cloud distribution; the point cloud distribution of the non-identification blind area obtained by the lidar in the actual measurement is obtained to obtain the actual occluded point cloud distribution.

[0121] Step 406 : Identify the waterlogged area and the wet area from the non-identification blind area according to the ideal obstructed point cloud distribution and the actual obstructed point cloud distribution.

[0122] Step 407: Obtain the area of ​​the waterlogged area and the area of ​​the wet area.

[0123] Specifically, after the water accumulation area and the wet area are determined, the area of ​​the water accumulation area and the area of ​​the wet area are obtained.

[0124] For example, the area of ​​the water accumulation area obtained by laser radar is 2m 2 , the wet area is 5m 2 .

[0125] Step 408: Obtain the area of ​​the ideal obstructed point cloud distribution region.

[0126] Specifically, the area of ​​the ideal obstructed point cloud distribution area of ​​the current lidar is obtained.

[0127] For example, the area of ​​the ideal obstructed point cloud distribution area obtained by LiDAR is 10m 2 .

[0128] Step 409 : Calculate the ratio of the area of ​​the waterlogged area to the area of ​​the ideal obstructed point cloud distribution area to obtain a first area ratio.

[0129] Specifically, the first area ratio is obtained by calculating the ratio of the area of ​​the water accumulation area to the area of ​​the ideal obstructed point cloud distribution area.

[0130] For example, the area of ​​the waterlogged area is 2m 2 , the ideal area of ​​the obstructed point cloud distribution area is 10m 2 , then the first area ratio is 1 / 5.

[0131] Step 410 : Calculate the ratio of the area of ​​the wet area to the area of ​​the ideal obstructed point cloud distribution area to obtain a second area ratio.

[0132] Specifically, the second area ratio is obtained by calculating the ratio of the area of ​​the wet area to the area of ​​the ideal obstructed point cloud distribution area.

[0133] For example, the wet area is 5m 2 , the ideal area of ​​the obstructed point cloud distribution area is 10m 2 , then the second area ratio is 1 / 2.

[0134] Step 411: When the first area ratio and / or the second area ratio exceeds a preset ratio threshold, it is determined that the performance of the laser radar does not meet the standard.

[0135] Specifically, when any ratio of the first area ratio and the second area ratio exceeds a preset ratio threshold, it is determined that the performance of the laser radar does not meet the standard, and the laser radar is controlled to send an alarm message to the user.

[0136] For example, the preset ratio threshold is 1 / 10, the first area ratio is 1 / 5, and the second area ratio is 1 / 2. The first area ratio and the second area ratio both exceed the preset ratio threshold. At this time, the performance of the laser radar does not meet the standard, and an alarm information that the laser radar performance does not meet the standard is pushed to the user terminal.

[0137] It should be understood that although Figure 2a 、 Figure 3 、 Figure 4 The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. In addition, Figure 2a 、 Figure 3 、 Figure 4 At least part of the steps may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least part of the sub-steps or stages of other steps.

[0138] The solution of the present application determines the non-identification blind area of ​​the laser radar; when no target object is placed in the non-identification blind area, the point cloud distribution of the non-identification blind area is calculated based on the characteristic information of the laser radar and the characteristic information of the ground to obtain an ideal unobstructed point cloud distribution; when a target object is placed in the non-identification blind area, the occluded point cloud of the target object is removed from the ideal unobstructed point cloud distribution to obtain an ideal obstructed point cloud distribution, and the point cloud distribution of the non-identification blind area measured by the laser radar is obtained to obtain an actual obstructed point cloud distribution; based on the ideal obstructed point cloud distribution and the actual obstructed point cloud distribution, water accumulation areas and wet areas are identified from the non-identification blind area; and the performance identification result of the laser radar is determined based on the area of ​​the water accumulation area and the area of ​​the wet area. That is, the solution of the present application can determine the non-identification blind area of ​​the laser radar, determine the water accumulation area and the wet area by calculating the point cloud distribution of the non-identification blind area in various situations, and then identify the laser radar performance based on the area of ​​each area, thereby enhancing the practicality and reliability of the laser radar.

[0139] Figure 5 This is a schematic diagram of the structure of the performance identification device of the laser radar provided in this application, which is suitable for executing the performance identification method of the laser radar provided in this application, such as Figure 5 As shown, the device may specifically include:

[0140] A determination module 501 is configured to determine a non-identification blind area of ​​the laser radar;

[0141] An unobstructed distribution module 502 is configured to calculate a point cloud distribution of the non-identification blind area based on characteristic information of the laser radar and characteristic information of the ground to obtain an ideal unobstructed point cloud distribution when no target object is placed in the non-identification blind area.

[0142] The occlusion distribution module 503 is configured to, when the target object is placed in the non-identification blind zone, remove the occlusion point cloud of the target object from the ideal unobstructed point cloud distribution to obtain an ideal occlusion point cloud distribution, and obtain the point cloud distribution of the non-identification blind zone measured by the laser radar to obtain an actual occlusion point cloud distribution;

[0143] an area recognition module 504 for identifying a waterlogged area and a wet area from the non-identification blind area according to the ideal obstructed point cloud distribution and the actual obstructed point cloud distribution;

[0144] The result recognition module 505 is used to determine the performance recognition result of the laser radar according to the area of ​​the water accumulation area and the area of ​​the wet area.

[0145] In one embodiment, the occlusion point cloud of the target object in the occlusion distribution module 503 is obtained by:

[0146] Obtaining bounding box information of the target object;

[0147] The occlusion point cloud of the target object is calculated according to the bounding box information of the target object.

[0148] In one embodiment, the region identification module 504 is specifically configured to:

[0149] Determining a potential waterlogging area from the non-identification blind area according to the ideal obstructed point cloud distribution and the actual obstructed point cloud distribution;

[0150] The water ponding area and the wet area are determined from among the potential water ponding areas.

[0151] In one embodiment, the region identification module 504 determines the potential waterlogging area from the non-identification blind area according to the ideal obstructed point cloud distribution and the actual obstructed point cloud distribution, including:

[0152] Determining a first point cloud missing area from the actual occluded point cloud distribution according to the ideal occluded point cloud distribution;

[0153] Calculating a ratio of the number of points in the missing area of ​​the first point cloud to the number of points in the ideal obstructed point cloud distribution;

[0154] If the ratio exceeds a preset value, determining a second point cloud missing area from an unobstructed area of ​​the actual obstructed point cloud distribution according to the ideal obstructed point cloud distribution;

[0155] When the area of ​​the second point cloud missing region exceeds a preset area value, the second point cloud missing region is determined as the potential water accumulation area.

[0156] In one embodiment, the region identification module 504 determines the waterlogging area from the potential waterlogging area, including:

[0157] Obtaining a projected point cloud distribution from the potential waterlogging area;

[0158] The waterlogged area is determined according to the distribution of the projected point cloud.

[0159] In one embodiment, the region identification module 504 obtains the distribution of the projected point cloud from the potential waterlogging area, including:

[0160] Obtaining point cloud distribution of the potential waterlogging area;

[0161] Obtaining a preset point cloud in the potential waterlogging area according to the characteristic information of the ground and the point cloud distribution of the potential waterlogging area, wherein the preset point cloud includes a point cloud in the potential waterlogging area that is lower than the ground;

[0162] Clustering the preset point cloud to obtain a preset point cloud cluster;

[0163] When the number of point clouds in the preset point cloud cluster exceeds a point cloud number threshold, the point clouds in the preset point cloud cluster are projected to a preset height above the ground according to feature information of the ground to obtain the projected point cloud distribution.

[0164] In one embodiment, the region identification module 504 determines the waterlogged area according to the distribution of the projected point cloud, including:

[0165] When the position features of the projected point cloud distribution match the actual obstructed point cloud distribution, calculating the number of laser beams reflected by the laser radar in the potential water accumulation area;

[0166] When the number of the laser beams exceeds a laser number threshold, the potential water accumulation area is determined as the water accumulation area.

[0167] In one embodiment, the region identification module 504 determines the wet region from the potential water accumulation region, including:

[0168] removing the water accumulation area from the potential water accumulation area to obtain a remaining potential water accumulation area;

[0169] Acquire a point cloud within a preset range around the remaining potential waterlogging area to obtain a point cloud within the preset range;

[0170] The wet area is determined according to the preset range point cloud.

[0171] In one embodiment, the region identification module 504 determines the wet region based on the preset range point cloud, including:

[0172] Calculating the mean reflection intensity of the point cloud within the preset range;

[0173] If the reflection intensity mean is lower than the intensity mean threshold, the remaining potential waterlogging area is recorded as an observation area;

[0174] Counting the number of times the remaining potential waterlogging area is recorded as an observation area;

[0175] When the number of times exceeds a threshold number of times, the remaining potential water accumulation area is determined as the wet area.

[0176] In one embodiment, the result identification module 505 is specifically configured to:

[0177] Obtaining the area of ​​the waterlogged area and the area of ​​the wet area;

[0178] Obtaining the area of ​​the ideal obstructed point cloud distribution region;

[0179] calculate a ratio of an area of the water accumulation region to an area of the ideal occluded point cloud distribution region, to obtain a first area ratio;

[0180] calculate a ratio of an area of the wet region to an area of the ideal occluded point cloud distribution region, to obtain a second area ratio;

[0181] determine the performance identification result of the lidar according to the first area ratio and / or the second area ratio.

[0182] In an embodiment, the result identification module 505 determines the performance identification result of the lidar according to the first area ratio and / or the second area ratio, including:

[0183] when the first area ratio and / or the second area ratio exceeds a preset ratio threshold, determine that the performance of the lidar is not up to standard.

[0184] It can be clearly understood by those skilled in the art that, for the convenience and brevity of description, only the division of the above functional modules is exemplified, and in actual application, the above functions can be completed by different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. The specific working process of the above described functional modules can refer to the corresponding process in the foregoing method embodiments, which will not be described here.

[0185] The device of the present application determines the non-identification blind area of the lidar; when no target object is placed in the non-identification blind area, calculates the point cloud distribution of the non-identification blind area according to the characteristic information of the lidar and the characteristic information of the ground, to obtain the ideal unoccluded point cloud distribution; when a target object is placed in the non-identification blind area, removes the occluded point cloud of the target object from the ideal unoccluded point cloud distribution, to obtain the ideal occluded point cloud distribution, and obtains the point cloud distribution of the non-identification blind area measured by the lidar, to obtain the actual occluded point cloud distribution; identifies the water accumulation region and the wet region from the non-identification blind area according to the ideal occluded point cloud distribution and the actual occluded point cloud distribution; determines the performance identification result of the lidar according to the area of the water accumulation region and the area of the wet region. That is, the scheme of the present application can determine the non-identification blind area of the lidar, determine the water accumulation region and the wet region by calculating the point cloud distribution of the non-identification blind area under various conditions, and then identify the performance of the lidar according to the area of each region, thereby enhancing the practicality and reliability of the lidar.

[0186] The present application also provides a vehicle comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor implements the performance identification method of the lidar provided in any of the above embodiments when executing the program.

[0187] The present application also provides a computer-readable medium having a computer program stored thereon, which, when executed by a processor, implements the performance identification method of the laser radar provided in any of the above embodiments.

[0188] Reference below Figure 6 , which shows a schematic structural diagram of a computer system 600 suitable for implementing the vehicle of the present application. Figure 6 The vehicle shown is only an example and should not bring any limitation to the function and scope of use of the present application.

[0189] like Figure 6 As shown, the computer system 600 includes a central processing unit (CPU) 601, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage portion 608 into a random access memory (RAM) 603. Various programs and data required for the operation of the computer system 600 are also stored in the RAM 603. The CPU 601, ROM 602, and RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0190] The following components are connected to the I / O interface 605: an input section 606 including a keyboard, a mouse, and the like; an output section 607 including devices such as a cathode ray tube (CRT), a liquid crystal display (LCD), and a speaker; a storage section 608 including a hard disk; and a communication section 609 including a network interface card such as a LAN card or a modem. The communication section 609 performs communication processing via a network such as the Internet. A drive 610 is also connected to the I / O interface 605 as needed. A removable medium 611, such as a magnetic disk, an optical disk, a magneto-optical disk, or a semiconductor memory, is installed in the drive 610 as needed, so that computer programs read therefrom can be installed into the storage section 608 as needed.

[0191] In particular, according to the embodiments disclosed in the present application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, the embodiments disclosed in the present application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program comprising program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via the communication section 609, and / or installed from a removable medium 611. When the computer program is executed by the central processing unit (CPU) 601, the above-mentioned functions defined in the system of the present application are executed.

[0192] It should be noted that the computer-readable medium shown in this application can be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any combination of the above. More specific examples of computer-readable storage media can include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this application, a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, device, or device. In this application, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, which carries computer-readable program code. This propagated data signal can take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport a program for use by or in conjunction with an instruction execution system, apparatus, or device. Program code embodied on a computer-readable medium may be transmitted using any suitable medium, including but not limited to wireless, wireline, optical fiber cable, RF, or any suitable combination thereof.

[0193] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, program segment, or a part of code, and the above-mentioned module, program segment, or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of the boxes in the block diagram or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0194] The modules and / or units described in the present application can be implemented by software or by hardware. The described modules and / or units can also be arranged in a processor, for example, can be described as: a processor includes a determination module, an unobstructed distribution module, an obstructed distribution module, a region identification module and a result identification module. In some cases, the names of these modules do not constitute a limitation on the modules themselves.

[0195] As another aspect, the present application also provides a computer readable medium, which can be included in the device described in the above embodiments, or can exist independently without being assembled into the device. The computer readable medium carries one or more programs, which, when executed by the device, cause the device to include:

[0196] The non-identification blind area of the laser radar is determined; when no target object is placed in the non-identification blind area, the point cloud distribution of the non-identification blind area is calculated according to the characteristic information of the laser radar and the characteristic information of the ground to obtain an ideal unobstructed point cloud distribution; when a target object is placed in the non-identification blind area, the obstructed point cloud of the target object is removed from the ideal unobstructed point cloud distribution to obtain an ideal obstructed point cloud distribution, and the point cloud distribution of the non-identification blind area measured by the laser radar is obtained to obtain an actual obstructed point cloud distribution; the water accumulation area and the wet area are identified from the non-identification blind area according to the ideal obstructed point cloud distribution and the actual obstructed point cloud distribution; and the performance identification result of the laser radar is determined according to the area of the water accumulation area and the area of the wet area.

[0197] According to the technical solution of the present application, the non-identification blind area of the laser radar is determined; when no target object is placed in the non-identification blind area, the point cloud distribution of the non-identification blind area is calculated according to the characteristic information of the laser radar and the characteristic information of the ground to obtain an ideal unobstructed point cloud distribution; when a target object is placed in the non-identification blind area, the obstructed point cloud of the target object is removed from the ideal unobstructed point cloud distribution to obtain an ideal obstructed point cloud distribution, and the point cloud distribution of the non-identification blind area measured by the laser radar is obtained to obtain an actual obstructed point cloud distribution; the water accumulation area and the wet area are identified from the non-identification blind area according to the ideal obstructed point cloud distribution and the actual obstructed point cloud distribution; and the performance identification result of the laser radar is determined according to the area of the water accumulation area and the area of the wet area. That is, the scheme of the present application can determine the non-identification blind area of the laser radar, identify the water accumulation area and the wet area by calculating the point cloud distribution of the non-identification blind area under various conditions, and identify the performance of the laser radar according to the areas of the regions, thereby enhancing the practicability and reliability of the laser radar.

[0198] The above specific embodiments do not constitute a limitation on the scope of protection of this application. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may occur depending on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this application shall be included within the scope of protection of this application.

Claims

1. A method for identifying the performance of a laser radar, characterized in that: The method comprises: Determining a non-identification blind area of ​​the laser radar; When no target object is placed in the non-identification blind area, the point cloud distribution of the non-identification blind area is calculated according to the characteristic information of the laser radar and the characteristic information of the ground to obtain an ideal unobstructed point cloud distribution; When the target object is placed in the non-identification blind area, the occluded point cloud of the target object is removed from the ideal unobstructed point cloud distribution to obtain an ideal occluded point cloud distribution, and the point cloud distribution of the non-identification blind area measured by the laser radar is obtained to obtain an actual occluded point cloud distribution; Identifying a waterlogged area and a wet area from the non-identification blind area according to the ideal obstructed point cloud distribution and the actual obstructed point cloud distribution; Obtaining the area of ​​the waterlogged area and the area of ​​the wet area; Obtaining the area of ​​the ideal obstructed point cloud distribution region; Calculating a ratio of an area of ​​the waterlogged area to an area of ​​the ideal obstructed point cloud distribution area to obtain a first area ratio; Calculating a ratio of the area of ​​the wet area to the area of ​​the ideal obstructed point cloud distribution area to obtain a second area ratio; When the first area ratio and / or the second area ratio exceeds a preset ratio threshold, it is determined that the performance of the laser radar does not meet the standards.

2. The method according to claim 1, characterized in that The occlusion point cloud of the target object is obtained by: Obtaining bounding box information of the target object; The occlusion point cloud of the target object is calculated according to the bounding box information of the target object.

3. The method according to claim 1, characterized in that The identifying of the water accumulation area and the wet area from the non-identification blind area according to the ideal obstructed point cloud distribution and the actual obstructed point cloud distribution includes: Determining a potential waterlogging area from the non-identification blind area according to the ideal obstructed point cloud distribution and the actual obstructed point cloud distribution; The water accumulation area and the wet area are determined from among the potential water accumulation areas.

4. The method according to claim 3, characterized in that The determining of a potential waterlogging area from the non-identification blind area according to the ideal obstructed point cloud distribution and the actual obstructed point cloud distribution includes: Determining a first point cloud missing area from the actual occluded point cloud distribution according to the ideal occluded point cloud distribution; Calculating a ratio of the number of points in the missing area of ​​the first point cloud to the number of points in the ideal obstructed point cloud distribution; If the ratio exceeds a preset value, determining a second point cloud missing area from the unobstructed area of ​​the actual distribution of the obstructed point cloud according to the number of points in the first point cloud missing area; When the area of ​​the second point cloud missing region exceeds a preset area value, the second point cloud missing region is determined as the potential water accumulation area.

5. The method according to claim 3, characterized in that The determining the waterlogging area from the potential waterlogging area comprises: Obtaining a projected point cloud distribution from the potential waterlogging area; The waterlogged area is determined according to the distribution of the projected point cloud.

6. The method according to claim 5, characterized in that Obtaining the projection point cloud distribution from the potential waterlogging area includes: Obtaining point cloud distribution of the potential waterlogging area; Obtaining a preset point cloud in the potential waterlogging area according to the characteristic information of the ground and the point cloud distribution of the potential waterlogging area, wherein the preset point cloud includes a point cloud in the potential waterlogging area that is lower than the ground; Clustering the preset point cloud to obtain a preset point cloud cluster; When the number of point clouds in the preset point cloud cluster exceeds a point cloud number threshold, the point clouds in the preset point cloud cluster are projected to a preset height above the ground according to feature information of the ground to obtain the projected point cloud distribution.

7. The method according to claim 6, characterized in that The determining the waterlogged area according to the distribution of the projected point cloud includes: When the position features of the projected point cloud distribution match the actual obstructed point cloud distribution, calculating the number of laser beams reflected by the laser radar in the potential water accumulation area; When the number of the laser beams exceeds a laser number threshold, the potential water accumulation area is determined as the water accumulation area.

8. The method according to claim 3, characterized in that The determining of the wet area from the potential water accumulation area comprises: removing the water accumulation area from the potential water accumulation area to obtain a remaining potential water accumulation area; Acquire a point cloud within a preset range around the remaining potential waterlogging area to obtain a point cloud within the preset range; The wet area is determined according to the preset range point cloud.

9. The method according to claim 8, characterized in that The determining the wet area according to the preset range point cloud includes: Calculating the mean reflection intensity of the point cloud within the preset range; If the reflection intensity mean is lower than the intensity mean threshold, the remaining potential waterlogging area is recorded as an observation area; Counting the number of times the remaining potential waterlogging area is recorded as an observation area; When the number of times exceeds a threshold number of times, the remaining potential water accumulation area is determined as the wet area.

10. A laser radar performance identification device, characterized in that: include: A determination module, configured to determine a non-identification blind area of ​​the laser radar; An unobstructed distribution module is used to calculate the point cloud distribution of the non-identification blind area according to the characteristic information of the laser radar and the characteristic information of the ground when no target object is placed in the non-identification blind area, so as to obtain an ideal unobstructed point cloud distribution; an occlusion distribution module, configured to, when the target object is placed in the non-identification blind zone, remove the occlusion point cloud of the target object from the ideal unobstructed point cloud distribution to obtain an ideal occlusion point cloud distribution, and obtain the point cloud distribution of the non-identification blind zone measured by the laser radar to obtain an actual occlusion point cloud distribution; an area recognition module, configured to recognize a waterlogged area and a wet area from the non-identification blind area according to the ideal obstructed point cloud distribution and the actual obstructed point cloud distribution; A result recognition module, used for obtaining the area of ​​the waterlogged area and the area of ​​the wet area; Obtaining the area of ​​the ideal obstructed point cloud distribution region; Calculating a ratio of an area of ​​the waterlogged area to an area of ​​the ideal obstructed point cloud distribution area to obtain a first area ratio; Calculating a ratio of the area of ​​the wet area to the area of ​​the ideal obstructed point cloud distribution area to obtain a second area ratio; When the first area ratio and / or the second area ratio exceeds a preset ratio threshold, it is determined that the performance of the laser radar does not meet the standards.

11. A vehicle comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the performance identification method of the laser radar as described in any one of claims 1 to 9 is implemented.

12. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the performance identification method of the laser radar as described in any one of claims 1 to 9 is implemented.

Images